Merge pull request keras-team#1566 from tpsatish95/master

added random_shear() to random_transform

docs/templates/preprocessing/image.md

@@ -10,6 +10,7 @@ keras.preprocessing.image.ImageDataGenerator(featurewise_center=True,
     rotation_range=0.,
     width_shift_range=0.,
     height_shift_range=0.,
+    shear_range=0.,
     horizontal_flip=False,
     vertical_flip=False)
 ```
@@ -25,24 +26,25 @@ Generate batches of tensor image data with real-time data augmentation. The data
     - __rotation_range__: Int. Degree range for random rotations.
     - __width_shift_range__: Float (fraction of total width). Range for random horizontal shifts.
     - __height_shift_range__: Float (fraction of total height). Range for random vertical shifts.
+    - __shear_range__: Float. Shear Intensity (Shear angle in counter-clockwise direction as radians)
     - __horizontal_flip__: Boolean. Randomly flip inputs horizontally.
     - __vertical_flip__: Boolean. Randomly flip inputs vertically.
 
 - __Methods__:
     - __fit(X)__: Required if featurewise_center or featurewise_std_normalization or zca_whitening. Compute necessary quantities on some sample data.
-        - __Arguments__: 
+        - __Arguments__:
             - __X__: sample data.
             - __augment__: Boolean (default: False). Whether to fit on randomly augmented samples.
             - __rounds__: int (default: 1). If augment, how many augmentation passes over the data to use.
     - __flow(X, y)__:
-        - __Arguments__: 
+        - __Arguments__:
             - __X__: data.
             - __y__: labels.
             - __batch_size__: int (default: 32).
             - __shuffle__: boolean (defaut: False).
-            - __save_to_dir__: None or str. This allows you to optimally specify a directory to which to save the augmented pictures being generated (useful for visualizing what you are doing). 
+            - __save_to_dir__: None or str. This allows you to optimally specify a directory to which to save the augmented pictures being generated (useful for visualizing what you are doing).
             - __save_prefix__: str. Prefix to use for filenames of saved pictures.
-            - __save_format__: one of "png", jpeg". 
+            - __save_format__: one of "png", jpeg".
 
 - __Example__:
 ```python
@@ -58,7 +60,7 @@ datagen = ImageDataGenerator(
     height_shift_range=0.2,
     horizontal_flip=True)
 
-# compute quantities required for featurewise normalization 
+# compute quantities required for featurewise normalization
 # (std, mean, and principal components if ZCA whitening is applied)
 datagen.fit(X_train)
 
@@ -77,4 +79,4 @@ for e in range(nb_epoch):
             # we need to break the loop by hand because
             # the generator loops indefinitely
             break
-```
+```

keras/preprocessing/image.py

@@ -60,10 +60,14 @@ def random_barrel_transform(x, intensity):
     pass
 
 
-def random_shear(x, intensity):
-    # TODO
-    pass
-
+def random_shear(x, intensity, fill_mode="nearest", cval=0.):
+    shear = random.uniform(-intensity, intensity)
+    shear_matrix = np.array([[1.0, -math.sin(shear), 0.0],
+                            [0.0, math.cos(shear), 0.0],
+                            [0.0, 0.0, 1.0]])
+    x = ndimage.interpolation.affine_transform(x, shear_matrix,
+                                               mode=fill_mode, order=3, cval=cval)
+    return x
 
 def random_channel_shift(x, rg):
     # TODO
@@ -132,8 +136,10 @@ def __init__(self,
                  rotation_range=0.,  # degrees (0 to 180)
                  width_shift_range=0.,  # fraction of total width
                  height_shift_range=0.,  # fraction of total height
+                 shear_range=0.,  # shear intensity (shear angle in radians)
                  horizontal_flip=False,
                  vertical_flip=False):
+
         self.__dict__.update(locals())
         self.mean = None
         self.std = None
@@ -206,7 +212,8 @@ def random_transform(self, x):
         if self.vertical_flip:
             if random.random() < 0.5:
                 x = vertical_flip(x)
-
+        if self.shear_range:
+            x = random_shear(x,self.shear_range)
         # TODO:
         # zoom
         # barrel/fisheye

tests/keras/preprocessing/test_image.py

@@ -45,6 +45,7 @@ def test_image_data_generator():
             rotation_range=90.,
             width_shift_range=10.,
             height_shift_range=10.,
+            shear_range=0.5,
             horizontal_flip=True,
             vertical_flip=True)
         generator.fit(images, augment=True)